# Reply style for Claude Code and Codex

Reply style is one short text that tells the agent how to write to you. You set it once, in Settings. The gateway adds it to every request from Claude Code and Codex, on every machine.

## Key facts

What it is

One short text, 4,096 characters at most, that tells the agent how to write to you.

Who it is for

Anyone who wants the same writing style from Claude Code and Codex.

Clients

Claude Code and Codex, through the gateway. Sessions that go direct to Anthropic or OpenAI do not get it.

Measured result

Not a cost feature, and not measured on its own. For the gateway as a whole, see [Benchmarks](https://context-mode.com/docs/benchmarks#pooled).

Limits

It changes wording only, not what the agent does. A longer text is refused, not cut.

## What it is

A reply style changes how the agent writes, not what it does. It adds no task. The gateway marks it as a standing writing rule, and says that your current message wins if the two disagree. So "Answer in one line" in a message beats a style that asks for detail.

## Where to set it

1. Open [Settings](https://console.context-mode.com/app/controls) in the console.
2. Find the **Reply style** card. It applies to every agent on your account.
3. Type or paste your text and click **Save**.

length 4,096 characters at most. A longer text is refused, not cut.

scope your account: Claude Code and Codex, on every machine

turn off clear the box and save. The gateway then adds nothing. On an account that has never saved a style, the box shows the default reply style below.

## Default reply style

This is the default. An account that has never saved a style gets this text, and the Reply style card in Settings shows it. Edit it and save to make it yours:

```
Talk to me in ASD-STE100 Simplified Technical English.
Writing rules, from Orwell, 1946. These govern prose: docs, PR text, messages. Never touch code or technical terms; swap in everyday words only where precision survives.

Never use a metaphor, simile or other figure of speech which you are used to seeing in print.
Never use a long word where a short one will do.
If it is possible to cut a word out, always cut it out.
Never use the passive where you can use the active.
Never use a foreign phrase, a scientific word or a jargon word if you can think of an everyday English equivalent.
When responding to me and creating text for me: Keep language concise and short, a 15yo should always be able to understand what you're writing. Avoid wall of text.
```

It is 756 characters, well under the limit. The first line asks for ASD-STE100, a controlled English made for aerospace maintenance manuals. The next line limits the rules to prose, so code and technical terms stay exact. Five lines are George Orwell's rules from 1946. The last line asks for short text.

**This full text is the built-in default.** An account that saved its own style keeps it. An account that cleared the box and saved gets no style.

A reply style that asks for short answers was on in every [benchmark](https://context-mode.com/docs/benchmarks) run through the gateway. [Context Saving](https://context-mode.com/docs/how-saving-works#limits) says how that affects the results.

## How it is applied

- **Every request.** The gateway adds the style to each request in a conversation, not only the first. The client's files and settings do not change.
- **At the start of the conversation, not in the system prompt.** The style goes at the start of the first message. The client's system prompt is never edited.
- **From the provider's cache.** The style sits in the part of the request that the provider caches. After the first request, it is charged at the cache read price, not as new input on every turn.
- **Stable during a conversation.** To keep that cache warm, the gateway holds the start of a conversation unchanged. A new style reaches a running conversation after 65 minutes without a request, and every new conversation at once.
- **Only where people read it.** Claude Code's helper calls, such as a session title or a page summary, get no style.
- **Added once.** If a client sends the style block back, the gateway does not add a second copy.

## Clients

Claude Code and Codex, through the gateway. Sessions that go direct to Anthropic or OpenAI do not get the style. Connect each machine with `npx @context-mode/cli`, as in the [quick start](https://context-mode.com/docs/quick-start).

## Compared with other approaches

| Approach | Where it lives | Clients | Who sets it |
| --- | --- | --- | --- |
| [Claude Code output styles](https://code.claude.com/docs/en/output-styles) | Built-in styles, such as Concise, or a custom style file. "To make a style your default across projects, set `outputStyle` in `~/.claude/settings.json` ." | Claude Code | You, per user; a project's own settings take precedence. Admins can ship styles in the managed settings folder. |
| [Claude Code CLAUDE.md](https://code.claude.com/docs/en/memory) | Files in the repo, in your home folder, or deployed by an admin | Claude Code | You, your team through git, or IT through a managed policy file that users cannot exclude |
| [Codex AGENTS.md](https://developers.openai.com/codex/memories) | Files you write | Codex | You. OpenAI's memories page says required team guidance belongs in AGENTS.md. |
| [Cursor rules](https://cursor.com/docs/context/rules) | Files in the project, plus team rules | Cursor | You, or a team admin for required team rules |
| Context Mode reply style | The gateway, one text per account | Claude Code and Codex | You, once, in Settings |

**Where they are stronger.** Claude Code output styles are first-party, set per user across projects, and need no third party. Instruction files are free, first-party and need no third party too. They can differ per project, and they can hold far more than writing rules: build steps, conventions and project facts. Cursor team rules let an admin require one rule for a whole team; a Context Mode reply style belongs to one account.

**Where Context Mode differs.** One text covers Claude Code and Codex, on every machine, with no file to copy into each repository. It is marked as a rule about wording only, so it does not add work.

## FAQ

### Does a reply style change what the agent does?

No. The gateway marks it as a standing rule about wording only, so it adds no task.

### How is it different from CLAUDE.md or AGENTS.md?

Those files live in a repository. A reply style belongs to your account and reaches every machine, in both clients.

### How do I turn it off?

Clear the box and save. The gateway then adds nothing.

Compared with other tools: see the [landscape](https://context-mode.com/docs/landscape#native).

[Quick start →](https://context-mode.com/docs/quick-start) [Context limit](https://context-mode.com/docs/context-limit) [Memory](https://context-mode.com/docs/memory)
